Zusammenfassung
Vorteile der künstlichen Intelligenz (KI)
Durch einen verantwortungsvollen, sicheren und erfolgreichen Einsatz der künstlichen Intelligenz (KI) im dermato-onkologischen Bereich können mögliche Vorteile entstehen: (1) die ärztlich-medizinische Arbeit kann sich auf Hautkrebspatienten fokussieren, (2) Patienten können rascher und effizienter versorgt werden bei zunehmender Hautkrebsinzidenz und parallel abnehmenden Zahlen beruflich aktiver Hautarzte, und (3) Anwender können von den KI-Ergebnissen lernen.
Potenzielle Nachteile und Gefahren des KI-Einsatzes
(1) Ein mangelndes Vertrauensverhältnis bei fehlendem Patienten-Arzt-Kontakt kann sich entwickeln, (2) ein zusätzlicher zeitlicher Aufwand kann durch die zeitnahe ärztliche Kontrolle von der KI als benigne eingestuften Hautläsionen entstehen, (3) ausreichende ärztliche Erfahrungen zum Erkennen und korrigieren fehlerhafter KI-Entscheidungen können fehlen, und (4) bei fehlerhafter KI-Entscheidung ist eine erneute Kontaktaufnahme zum Patienten zur zeitnahen Vorstellung notwendig. Ungeklärt sind bisher bei der KI-Anwendung die medizinisch-rechtliche Situation sowie die finanzielle Vergütung. Apps mit KI erbringen auf Basis von klinischen Bildern von Hauttumoren aktuell keine ausreichende diagnostische Hilfe.
Voraussetzungen und möglicher Nutzen von Smartphone-Programm-Applikationen
Smartphone-Programm-Applikationen (Apps) können verantwortungsvoll erfolgreich eingesetzt werden, wenn die Bildqualität gut ist, anamnestische Angaben unkompliziert eingegeben werden können, die Bild- und Befundübermittlung gesichert ist und medizinrechtliche sowie finanzielle Fragen geklärt sind. Apps können als krankheitsspezifisches Informationsmaterial eingesetzt werden und in der Teledermatologie die Patientenversorgung optimieren.
Abstract
Advantages of artificial intelligence (AI)
With responsible, safe and successful use of artificial intelligence (AI), possible advantages in the field of dermato-oncology include the following: (1) medical work can focus on skin cancer patients, (2) patients can be more quickly and effectively treated despite the increasing incidence of skin cancer and the decreasing number of actively working dermatologists and (3) users can learn from the AI results.
Potential disadvantages and risks of AI use
(1) Lack of mutual trust can develop due to the decreased patient–physician contact, (2) additional time effort will be necessary to promptly evaluate the AI-classified benign lesions, (3) lack of adequate medical experience to recognize misclassified AI decisions and (4) recontacting a patient in due time in the case of incorrect AI classifications. Still problematic in the use of AI are the medicolegal situation and remuneration. Apps using AI currently cannot provide sufficient assistance based on clinical images of skin cancer.
Requirements and possible use of smartphone program applications
Smartphone program applications (apps) can be implemented responsibly when the image quality is good, the patient’s history can be entered easily, transmission of the image and results are assured and medicolegal aspects as well as remuneration are clarified. Apps can be used for disease-specific information material and can optimize patient care by using teledermatology.
Literatur
Wikipedia (2020) Artificial intelligence. https://en.wikipedia.org/wiki/Artificial_intelligence. Zugegriffen: 13. Apr. 2020
Wallis C (2019) How artificial intelligence will change medicine. Nature 576(7787):48
Lallas A, Argenziano G (2018) Artificial intelligence and melanoma diagnosis: ignoring human nature may lead to false predictions. Dermatol Pract Concept 8(4):249–251
Navarrete-Dechent C, Dusza SW, Liopyris K, Marghoob AA, Halpern AC, Marchetti MA (2018) Automated dermatological diagnosis: hype or reality? J Invest Dermatol 138(10):2277–2279
Tschandl P (2019) Problems and potentials of automated object detection for skin cancer recognition. JAMA Dermatol. https://doi.org/10.1001/jamadermatol.2019.3360
Wikipedia (2020) Artificial intelligence in healthcare. https://en.wikipedia.org/wiki/Artificial_intelligence_in_healthcare. Zugegriffen: 13. Apr. 2020
Wikipedia (2020) Computer-aided diagnosis. https://en.wikipedia.org/wiki/Computer-aided_diagnosis. Zugegriffen: 13. Apr. 2020
Binder M, Steiner A, Schwarz M et al (1994) Application of an artificial neural network in epiluminescence microscopy pattern analysis of pigmented skin lesions: a pilot study. Br J Dermatol 130:460–465
Ercal F, Chawla A, Stoecker WV, Lee HC, Moss RH (1994) Neural network diagnosis of malignant melanoma from color images. IEEE Trans Biomed Eng 41(9):837–845
Dreiseitl S, Binder M, Hable K, Kittler H (2009) Computer versus human diagnosis of melanoma: evaluation of the feasibility of an automated diagnostic system in a prospective clinical trial. Melanoma Res 19(3):180–184
Dick V, Sinz C, Mittlböck M, Kittler H, Tschandl P (2019) Accuracy of computer-aided diagnosis of melanoma: a meta-analysis. JAMA Dermatol. https://doi.org/10.1001/jamadermatol.2019.1375
Esteva A, Kuprel B, Novoa RA et al (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639):115–118
Brinker TJ, Hekler A, Utikal JS et al (2018) Skin cancer classification using convolutional neural networks: systematic review. J Med Internet Res 20(10):e11936
Haenssle HA, Fink C, Schneiderbauer R et al (2018) Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Ann Oncol 29:1836–1842
Narla A, Kuprel B, Sarin K et al (2018) Automated classification of skin lesions: from pixels to practice. J Invest Dermatol 138:2108–2110
Brinker TJ, Hekler A, Enk AH et al (2019) Deep neural networks are superior to dermatologists in melanoma image classification. Eur J Cancer 119:11–17
Brinker TJ, Hekler A, Enk AH et al (2019) Deep learning outperformed 136 of 157 dermatologists in a head-to-head dermoscopic melanoma image classification task. Eur J Cancer 113:47–54
Fink C, Blum A, Buhl T et al (2019) Diagnostic performance of a deep learning convolutional neural network in the differentiation of combined nevi and melanomas. J Eur Acad Dermatol Venereol. https://doi.org/10.1111/jdv.16165
Tschandl P, Rosendahl C, Akay BN et al (2019) Expert-level diagnosis of nonpigmented skin cancer by combined convolutional neural networks. JAMA Dermatol 155:58–65
Tschandl P, Codella N, Akay BN et al (2019) Comparison of the accuracy of human readers versus machine-learning algorithms for pigmented skin lesion classification: an open, web-based, international, diagnostic study. Lancet Oncol 20:938–947
Winkler JK, Sies K, Fink C et al (2020) Melanoma recognition by a deep learning convolutional neural network—Performance in different melanoma subtypes and localisations. Eur J Cancer 127:21–29
Haenssle HA, Fink C, Toberer F et al (2020) Man against machine reloaded: performance of a market-approved convolutional neural network in classifying a broad spectrum of skin lesions in comparison with 96 dermatologists working under less artificial conditions. Ann Oncol 31(1):137–143
Han SS, Moon IJ, Lim W et al (2020) Keratinocytic skin cancer detection on the face using region-based convolutional neural network. JAMA Dermatol 156(1):29–37
Tschandl P, Argenziano G, Razmara M, Yap J (2019) Diagnostic accuracy of content-based dermatoscopic image retrieval with deep classification features. Br J Dermatol 181(1):155–165
Li Y, Esteva A, Kuprel B, Novoa R, Ko J, Thrun S (2016) Skin cancer detection and tracking using data synthesis and deep learning (arXiv:1612.01074)
Blum A, Hofmann-Wellenhof R, Luedtke H et al (2004) Value of the clinical history for different users of dermoscopy compared with results of digital analysis. J Eur Acad Dermatol Venereol 18:665–669
Tschandl P, Rosendahl C, Kittler H (2018) The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci Data 5:180161
Marchetti MA, Liopyris K, Dusza SW et al (2020) Computer algorithms show potential for improving dermatologists’ accuracy to diagnose cutaneous melanoma: Results of the International Skin Imaging Collaboration 2017. J Am Acad Dermatol 82(3):622–627
Winkler JK, Fink C, Toberer F et al (2019) Association between surgical skin markings in dermoscopic images and diagnostic performance of a deep learning convolutional neural network for melanoma recognition. JAMA Dermatol. https://doi.org/10.1001/jamadermatol.2019.1735
Shrivastava VK, Londhe ND, Sonawane RS, Suri JS (2016) Computer-aided diagnosis of psoriasis skin images with HOS, texture and color features: a first comparative study of its kind. Comput Methods Programs Biomed 126:98–109
Han SS, Park GH, Lim W, Kim MS, Na JI, Park I, Chang SE (2018) Deep neural networks show an equivalent and often superior performance to dermatologists in onychomycosis diagnosis: automatic construction of onychomycosis datasets by region-based convolutional deep neural network. PLoS ONE 13(1):e191493
Melina A, Dinh NN, Tafuri B et al (2018) Artificial intelligence for the objective evaluation of acne investigator global assessment. J Drugs Dermatol 17(9):1006–1009
Bobrova M, Taranik M, Kopanitsa G (2019) Using neural networks for diagnosing in dermatology. Stud Health Technol Inform 261:211–216
Li CX, Shen CB, Xue K et al (2019) Artificial intelligence in dermatology: past, present, and future. Chin Med J 132(17):2017–2020
Schlessinger DI, Chhor G, Gevaert O, Swetter SM, Ko J, Novoa RA (2019) Artificial intelligence and dermatology: opportunities, challenges, and future directions. Semin Cutan Med Surg 38(1):E31–37
Seité S, Khammari A, Benzaquen M, Moyal D, Dréno B (2019) Development and accuracy of an artificial intelligence algorithm for acne grading from smartphone photographs. Exp Dermatol 28(11):1252–1257
Hogarty DT, Su JC, Phan K et al (2020) Artificial intelligence in dermatology—Where we are and the way to the future: a review. Am J Clin Dermatol 21(1):41–47
Anonymous (2020) Checkliste für Gesundheits-Apps. Qualität, Nutzen, Transparenz und Datenschutz weisen große Unterschiede auf. Arztebl Baden Wurtt 04:199
bitkom (2019) Digital health. https://www.bitkom.org/sites/default/files/2019-05/190508_bitkom-pressekonferenz_e-health_prasentation.pdf. Zugegriffen: 13. Apr. 2020
Börve A, Terstappen K, Sandberg C, Paoli J (2013) Mobile teledermoscopy—There’s an app for that! Dermatol Pract Concept. https://doi.org/10.5826/dpc.0302a05
Augustin M, Wimmer J, Biedermann T, Blaga R, Dierks C, Djamei V et al (2018) Praxis der Teledermatologie. J Dtsch Dermatol Ges 16(Suppl 5):6–57
Dahlén Gyllencreutz J, Johansson Backman E, Terstappen K, Paoli J (2018) Teledermoscopy images acquired in primary health care and hospital settings—A comparative study of image quality. J Eur Acad Dermatol Venereol 32(6):1038–1043
Freeman EE, Semeere A, Osman H et al (2018) Smartphone confocal microscopy for imaging cellular structures in human skin in vivo. Biomed Opt Express 9(4):1906–1915
Alves J, Moreira D, Alves P, Rosado L, Vasconcelos MJM (2019) Automatic focus assessment on dermoscopic images acquired with smartphones. Sensors (Basel) 19(22):4957
Blum A, Haase S, Barlinn S et al (2020) Erfolgreiche regionale tele-dermatologische und tele-dermatoskopische Triage-Vernetzung zwischen niedergelassen Hausärzten und Hautärzten. Hautarzt. https://doi.org/10.1007/s00105-020-04584-5
Marek AJ, Chu EY, Ming ME, Khan ZA, Kovarik CL (2018) Piloting the use of smartphones, reminders, and accountability partners to promote skin self-examinations in patients with total body photography: a randomized controlled trial. Am J Clin Dermatol 19(5):779–785
Verzantvoort NCM, Teunis T, Verheij TJM, van der Velden AW (2018) Self-triage for acute primary care via a smartphone application: practical, safe and efficient? PLoS ONE 13(6):e199284
Petrie T, Samatham R, Goodyear SM, Webster DE, Leachman SA (2019) MoleMapper: an application for crowdsourcing mole images to advance melanoma early-detection research. Semin Cutan Med Surg 38(1):E49–E56
Walter FM, Pannebakker MM, Barclay ME et al (2020) Effect of a skin self-monitoring smartphone application on time to physician consultation among patients with possible melanoma: a phase 2 randomized clinical trial. JAMA Netw Open 3(2):e200001
Nair HKR (2018) Increasing productivity with smartphone digital imagery wound measurements and analysis. J Wound Care 27(Sup9a):S12–S19
Safdari R, Firoz A, Masoorian H (2017) Identifying training and informational components to develop a psoriasis self-management application. Med J Islam Repub Iran 1(31):67
Lacy FA, Coman GC, Holliday AC, Kolodney MS (2018) Assessment of smartphone application for teaching intuitive visual diagnosis of melanoma. JAMA Dermatol 154(6):730–731
van Galen LS, Xu X, Koh MJA, Thng S, Car J (2020) Eczema apps conformance with clinical guidelines: a systematic assessment of functions, tools and content. Br J Dermatol 182(2):444–453
Chuchu N, Takwoingi Y, Dinnes J et al (2018) Smartphone applications for triaging adults with skin lesions that are suspicious for melanoma. Cochrane Database Syst Rev 4(12):CD13192
Börve A, Dahlén Gyllencreutz J et al (2015) Smartphone teledermoscopy referrals: a novel process for improved triage of skin cancer patients. Acta Derm Venereol 95(2):186–190
Nami N, Massone C, Rubegni P, Cevenini G, Fimiani M, Hofmann-Wellenhof R (2015) Concordance and time estimation of store-and-forward mobile teledermatology compared to classical face-to-face consultation. Acta Derm Venereol 95(1):35–39
Vestergaard T, Prasad SC, Schuster A, Laurinaviciene R, Andersen MK, Bygum A (2020) Diagnostic accuracy and interobserver concordance: teledermoscopy of 600 suspicious skin lesions in Southern Denmark. J Eur Acad Dermatol Venereol. https://doi.org/10.1111/jdv.16275
Gilling S, Mortz CG, Vestergaard T (2020) Patient satisfaction and expectations regarding mobile teledermoscopy in general practice for diagnosis of non-melanoma skin cancer and malignant melanoma. Acta Derm Venereol. https://doi.org/10.2340/00015555-3459
Gracey LE, Zan S, Gracz J (2018) Use of user-centered design to create a smartphone application for patient-reported outcomes in atopic dermatitis. NPJ Digit Med 13(1):33
Devrim İ, Düzgöl M, Kara A et al (2019) Reliability and accuracy of smartphones for paediatric infectious disease consultations for children with rash in the paediatric emergency department. BMC Pediatr 19(1):40
Ming A, Walter I, Alhajjar A, Leuckert M, Mertens PR (2019) Study protocol for a randomized controlled trial to test for preventive effects of diabetic foot ulceration by telemedicine that includes sensor-equipped insoles combined with photo documentation. Trials 20(1):521
Blum A, Giacomel J (2015) “Tape dermatoscopy”: constructing a low-cost dermatoscope using a mobile phone, immersion fluid and transparent adhesive tape. Dermatol Pract Concept 5(2):87–93
Blum A, Oberhoff M, Oberhoff A (2019) Diskrete Nagelpigmentierung als ein Hinweis für ein frühes Melanom. Dtsch Arztebl Int 116:335
Brinker TJ, Hekler A, von Kalle C et al (2018) Teledermatology: comparison of store-and-forward versus live interactive video conferencing. J Med Internet Res 20(10):e11871
Finnane A, Soyer HP (2015) Smartphone diagnosis of skin cancer: there’s not yet an app for that. Br J Dermatol 172(6):1474–1475
Ngoo A, Finnane A, McMeniman E, Tan JM, Janda M, Soyer HP (2018) Efficacy of smartphone applications in high-risk pigmented lesions. Australas J Dermatol 59(3):e175–e182
Chung Y, van der Sande AAJ, de Roos KP et al (2020) Poor agreement between the automated risk assessment of a smartphone application for skin cancer detection and the rating by dermatologists. J Eur Acad Dermatol Venereol 34(2):274–278
Freeman K, Dinnes J, Chuchu N et al (2020) Algorithm based smartphone apps to assess risk of skin cancer in adults: systematic review of diagnostic accuracy studies. BMJ 368:m127
Udrea A, Mitra GD, Costea D et al (2020) Accuracy of a smartphone application for triage of skin lesions based on machine learning algorithms. J Eur Acad Dermatol Venereol 34(3):648–655
Acharya P, Mathur M (2020) Smartphone applications for the triage of skin lesions using machine learning: time to integrate the clinical information? J Eur Acad Dermatol Venereol. https://doi.org/10.1111/jdv.16371
Errichetti E, Zalaudek I, Kittler H et al (2020) Standardization of dermoscopic terminology and basic dermoscopic parameters to evaluate in general dermatology (non-neoplastic dermatoses): an expert consensus on behalf of the International Dermoscopy Society. Br J Dermatol 182:454–467
Nwko-Mohamadi M, Masenga JE, Mavura D et al (2019) Dermoscpic features of psoriasis, lichen planus and pityriasis rosea in patients with skin types IV and darker attending the regional dermatology training centre of Nothern Tanzania. Dermatol Pract Concept 9(1):44–51
Deeks JJ, Dinnes J, Williams HC (2020) Sensitivity and specificity of skinvision are likely to have been overestimated. J Eur Acad Dermatol Venereol. https://doi.org/10.1111/jdv.16371
Panda N, Solsky I, Huang EJ et al (2019) Using Smartphones to capture novel recovery metrics after cancer surgery. JAMA Surg 28:1–7
Ruiz AJ, LaRochelle EPM, Gunn JR et al (2019) Smartphone fluorescence imager for quantitative dosimetry of protoporphyrin-IX-based photodynamic therapy in skin. J Biomed Opt 25(6):1–13
DaCunha M, Habashi-Daniel A, Hanson C, Nichols E, Fraga GR (2020) A smartphone application to improve the precision of biopsy site identification: a proof-of-concept study. Health Informatics J. https://doi.org/10.1177/1460458220910341
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Interessenkonflikt
A. Blum erhielt Vortragshonorare und Reisekostenerstattungen von Almirall Hermal GmbH, Dermatologische Fortbildungsgesellschaft (DERFO), Heine Optotechnik GmbH, HealthCert, JuDerm im BVDD, FotoFinder Systems GmbH, La Roche Posay und MELAsciences Incorporation. H. Haenssle erhielt Honorare und Reisekostenerstattungen von Jenlab GmbH, Heine Optotechnik GmbH, Scibase AB, FotoFinder Systems GmbH, Magnosco GmbH und MELAsciences Incorporation. C. Fink erhielt Vortragshonorare und Reisekostenerstattungen von Almirall Hermal GmbH und Magnosco GmbH. R. Hofmann-Wellenhof ist Gründer und Teilhaber der teledermatologischen Firma e‑derm-consult GesmbH und erhielt Vortraghonorare von Fotofinder GesmbH. I. Zalaudek erhielt Referentenhonorare oder Kostenerstattung als passiver Teilnehmer: Honorar: Novartis Oncology and Immunology, Sanofi Genzyme Oncology, Sun Pharma. Kostenerstattung: Pierre Fabre, Roche Oncology. – Bezahlter Berater/interner Schulungsreferent/Gehaltsempfänger o. Ä.: Berater: Heine Optotechnik GmbH, FotoFinder Systems GmbH, Novartis Oncology, Sanofi Genzyme Oncology. H. Kittler erhielt Referentenhonorare von Almirall Hermal GmbH, Eli Lilly, La Roche Posay und Pelpharma und Unterstützung über Bereitstellung von Hard- oder Software von Derma Medical, Heine Optotechnik GmbH, Fotofinder Systems GmbH und 3Gen. P. Tschandl hat von MetaOptima Technology Inc. 2017 eine einjährige Post-Doc-Forschungsfinanzierung erhalten. S. Bosch gibt an, dass kein Interessenkonflikt besteht.
Für diesen Beitrag wurden von den Autoren keine Studien an Menschen oder Tieren durchgeführt. Für die aufgeführten Studien gelten die jeweils dort angegebenen ethischen Richtlinien.
Additional information
Aufgrund der besseren Lesbarkeit wurde auf eine genderkonforme Schreibweise verzichtet.
Rights and permissions
About this article
Cite this article
Blum, A., Bosch, S., Haenssle, H.A. et al. Künstliche Intelligenz und Smartphone-Programm-Applikationen (Apps). Hautarzt 71, 691–698 (2020). https://doi.org/10.1007/s00105-020-04658-4
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00105-020-04658-4